Create an audience

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is known. The description adds real value beyond that by stating "Changes the live account" and by imposing a compliance constraint (use only data you have rights and consents for under Pinterest's Ad Data Terms), which is a behavioral restriction an agent could not infer from structured fields. It still omits permission requirements and validation behavior for malformed rules.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short blocks: the effect statement first, then a compact per-type rule reference. Every line of the example block supplies distinct, non-redundant information, and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the annotations cover idempotency and safety. For a 5-parameter mutation with a free-form nested object, the description supplies the hardest missing piece (the rule shape per type) plus the live-account and data-rights warnings; only the identity/account parameters remain unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the nested `rule` object is merely additionalProperties:true, so the description carries the full burden here — and it does so well by enumerating the four audience_type values and giving a concrete JSON rule shape for each. It leaves name, description, and ad_account_id (nullable, presumably a default-account fallback) undocumented, which keeps it short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ("Create an audience for targeting"), which is clearly distinct from sibling operations like get_audience, list_audiences, and update_audience. It does not explicitly name those siblings, but the create-vs-read/update split is unambiguous from the verb alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The audience_type examples imply which kind of audience to build and when each rule shape applies, which is genuinely helpful context. However, there is no explicit routing guidance against alternatives such as pinterest_ads_create_customer_list, update_audience, or estimate_audience_size, and no stated prerequisites (permissions, ad account requirements).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.